Financial Reader™
Automate routine operations of extracting account numbers, important money values, dates and amounts from financial documents with complex layouts. Lymba’s Financial Reader™ extracts entities and relations from a variety of complex financial documents with differing layouts and formats. It also considers the document visual layout and structure which many NLP technologies miss. These various dissimilar inputs are unified within a single tool to streamline data access with custom formatting and easy integration.
Use Cases
Regulatory Compliance Document Comparison: A United States government agency wanted to compare their regulations to international standards to make sure that all safety standards were being met. Normally SMEs would manually review and memorize the contents of international regulations. This proved to be unscalable, costly ,and time consuming.
Operational Risk Assessment: A global investment bank needed a way for non-technical users to effectively retrieve information from graph databases. This was done to save time and streamline workflow. They wanted SMEs to be able to query the database without a technical person writing queries.
Investment Research QA: A global investment bank’s research team needed a way to search through thousands of internal and external reports to provide client guidance. These documents have ambiguous phrases, like “driving performance,” with specific meanings in the financial domain. Lymba developed a solution that understands industry specific jargon.
Lease Contract Analysis: A “Big 4” Accounting firm needed to speed up the review of their client’s lease agreements, extracting specific clauses and rates. They wanted to categorize leases based on which contracts held certain provisions or attributes. Manually reviewing thousands of thirty-page contracts is time consuming, costly, and prone to errors. Skilled reviewers’ fatigue after a few hours of reading similarly worded documents. An option they investigated was outsourcing the review to less expensive workers overseas. However, time and accuracy were still an issue.
Dodd Frank Act Overhaul: A billion-dollar global investment bank needed a way to identify critical contracts and potential violations to comply with the Dodd-Frank Act. Originally, they sent vendor contracts to a third-party offshore team to manually flag suspect language, which took a large amount of time to review. By utilizing our NLP platform, our client was able to cut down review time, costs, and improved accuracy.
Outcome: Lymba has helped speed up the review of financial documents in a variety of languages while cutting down costs and increasing accuracy. Pair with NL2Query™ to access extracted knowledge with plain English queries or Doc2Graph™ to populate a knowledge graph.